Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Pairwise engagement prediction on Corridor 7
Loading...
73
Accuracy
Qwen
33.584
43.817
54.05
64.283
Mar 19, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
Qwen
strategy=S1
2026.03
73
InternVL
strategy=S5
2026.03
70
InternVL
strategy=S6
2026.03
70
InternVL
strategy=S4
2026.03
67.6
Majority-class baseline
mode=Majority baseline
2026.03
64.9
Qwen
strategy=S4
2026.03
64.9
GPT-4o
strategy=S1
2026.03
59.5
GPT-4o
strategy=S2
2026.03
56.8
InternVL
strategy=S1
2026.03
51.4
InternVL
strategy=S3
2026.03
51.4
Qwen
strategy=S2
2026.03
51.4
Qwen
strategy=S5
2026.03
50
Qwen
strategy=S6
2026.03
50
InternVL
strategy=S2
2026.03
40.5
Qwen
strategy=S3
2026.03
35.1
Feedback
Search any
task
Search any
task
